{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:26LJYCM6YB654LEKAV4GXA7NH2","short_pith_number":"pith:26LJYCM6","schema_version":"1.0","canonical_sha256":"d7969c099ec07dde2c8a05786b83ed3e85c62ccdc5ac013f404b0136344d5110","source":{"kind":"arxiv","id":"2605.20729","version":1},"attestation_state":"computed","paper":{"title":"MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abudukeyumu Abudula, Bei Li, Jingang Wang, Jingbo Zhu, Junhao Ruan, Kechen Jiao, Tong Xiao, Xin Chen, Xinyu Liu, Xunliang Cai, Yongjing Yin","submitted_at":"2026-05-20T05:26:35Z","abstract_excerpt":"Accurate evaluation of conversational retrieval is pivotal for advancing Retrieval-Augmented Generation (RAG) systems. However, existing conversational retrieval benchmarks suffer from costly, sparse human annotation or rigid, unnatural automated heuristics. To address these challenges, we introduce MTR-Suite, a unified framework for auditing, synthesizing, and benchmarking retrieval. It features: (1) MTR-Eval, an LLM-based auditor quantifying alignment gaps in previous benchmarks; (2) MTR-Pipeline, a multi-agent system using greedy traversal clustering to generate high-fidelity dialogues at 1"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.20729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T05:26:35Z","cross_cats_sorted":[],"title_canon_sha256":"5baff2d0f8643ab8e2c222b207e04e2b26e719e35dc8da2c37dfd7b98875dca0","abstract_canon_sha256":"acf88f4ef6fdef2e6f20e6681c131d70425bc3af26f4d6f1b027c043d38606b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:51.152741Z","signature_b64":"GhgHtBzRZTqPUsqQrJD626hBG+k3YrsQfXviIAN34NPPNn1wDIg7KfnHQGYZwbfE6JzFcO7KhYXHZh9KlSH/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7969c099ec07dde2c8a05786b83ed3e85c62ccdc5ac013f404b0136344d5110","last_reissued_at":"2026-05-21T01:04:51.152013Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:51.152013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abudukeyumu Abudula, Bei Li, Jingang Wang, Jingbo Zhu, Junhao Ruan, Kechen Jiao, Tong Xiao, Xin Chen, Xinyu Liu, Xunliang Cai, Yongjing Yin","submitted_at":"2026-05-20T05:26:35Z","abstract_excerpt":"Accurate evaluation of conversational retrieval is pivotal for advancing Retrieval-Augmented Generation (RAG) systems. However, existing conversational retrieval benchmarks suffer from costly, sparse human annotation or rigid, unnatural automated heuristics. To address these challenges, we introduce MTR-Suite, a unified framework for auditing, synthesizing, and benchmarking retrieval. It features: (1) MTR-Eval, an LLM-based auditor quantifying alignment gaps in previous benchmarks; (2) MTR-Pipeline, a multi-agent system using greedy traversal clustering to generate high-fidelity dialogues at 1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20729","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.20729/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.20729","created_at":"2026-05-21T01:04:51.152142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20729v1","created_at":"2026-05-21T01:04:51.152142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20729","created_at":"2026-05-21T01:04:51.152142+00:00"},{"alias_kind":"pith_short_12","alias_value":"26LJYCM6YB65","created_at":"2026-05-21T01:04:51.152142+00:00"},{"alias_kind":"pith_short_16","alias_value":"26LJYCM6YB654LEK","created_at":"2026-05-21T01:04:51.152142+00:00"},{"alias_kind":"pith_short_8","alias_value":"26LJYCM6","created_at":"2026-05-21T01:04:51.152142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26LJYCM6YB654LEKAV4GXA7NH2","json":"https://pith.science/pith/26LJYCM6YB654LEKAV4GXA7NH2.json","graph_json":"https://pith.science/api/pith-number/26LJYCM6YB654LEKAV4GXA7NH2/graph.json","events_json":"https://pith.science/api/pith-number/26LJYCM6YB654LEKAV4GXA7NH2/events.json","paper":"https://pith.science/paper/26LJYCM6"},"agent_actions":{"view_html":"https://pith.science/pith/26LJYCM6YB654LEKAV4GXA7NH2","download_json":"https://pith.science/pith/26LJYCM6YB654LEKAV4GXA7NH2.json","view_paper":"https://pith.science/paper/26LJYCM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20729&json=true","fetch_graph":"https://pith.science/api/pith-number/26LJYCM6YB654LEKAV4GXA7NH2/graph.json","fetch_events":"https://pith.science/api/pith-number/26LJYCM6YB654LEKAV4GXA7NH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26LJYCM6YB654LEKAV4GXA7NH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26LJYCM6YB654LEKAV4GXA7NH2/action/storage_attestation","attest_author":"https://pith.science/pith/26LJYCM6YB654LEKAV4GXA7NH2/action/author_attestation","sign_citation":"https://pith.science/pith/26LJYCM6YB654LEKAV4GXA7NH2/action/citation_signature","submit_replication":"https://pith.science/pith/26LJYCM6YB654LEKAV4GXA7NH2/action/replication_record"}},"created_at":"2026-05-21T01:04:51.152142+00:00","updated_at":"2026-05-21T01:04:51.152142+00:00"}